Edit videos with OpenClaw

OpenClaw is the open-source, self-hosted personal AI agent that connects your favorite chat apps (Slack, Telegram, WhatsApp, Discord, iMessage, and more) to AI agents on your own machine. Add PandaStudio as an MCP server and you can edit videos by messaging OpenClaw from anywhere.

1

Install PandaStudio + OpenClaw

PandaStudio from writepanda.ai. OpenClaw installs from npm:

bash
npm install -g openclaw@latest

Then run openclaw onboard --install-daemon to set up the gateway and connect your first chat channel. Verify with openclaw --version.

2

Install Node.js if missing

bash
node --version

Need 18+ (OpenClaw itself needs it too). OpenClaw spawns the PandaStudio MCP server via npx, which needs Node on PATH. nodejs.org.

3

Enable PandaStudio's automation server + copy the token

PandaStudio's automation server is localhost-only and gated by a bearer token. To find your token:

  1. Open PandaStudio on your machine.
  2. Go to Settings → Automation.
  3. Toggle Enable automation server on. A bearer token will appear — copy it.

The token is a random 32-byte secret stored in your OS keychain. It never leaves your machine — agents only need it because the local HTTP server requires it on every request.

4

Install the PandaStudio Skill

The Skill teaches OpenClaw's agent PandaStudio's full command surface. Run once:

bash
npx skills add kamskans/pandastudio-skills

The installer detects OpenClaw and copies the Skill into its skills directory.

5

Register PandaStudio as an MCP server

Fastest is the CLI. Replace paste-your-token-here with the token from Step 3:

bash
openclaw mcp add pandastudio \
  --command npx \
  --arg -y \
  --arg @writepanda/mcp \
  --env PANDASTUDIO_TOKEN=paste-your-token-here

Or edit ~/.openclaw/openclaw.json directly and add the server under mcp.servers:

~/.openclaw/openclaw.json
{
  "mcp": {
    "servers": {
      "pandastudio": {
        "command": "npx",
        "args": ["-y", "@writepanda/mcp"],
        "env": {
          "PANDASTUDIO_TOKEN": "paste-your-token-here"
        }
      }
    }
  }
}
6

Reload OpenClaw and verify

Pick up the new server without restarting the whole daemon:

bash
openclaw mcp reload

Confirm it started and is exposing tools:

bash
openclaw mcp doctor pandastudio --probe
7

Message OpenClaw to drive PandaStudio

From any connected channel (Slack, Telegram, WhatsApp, Discord, your terminal), message OpenClaw:

  • "Open my latest recording, transcribe it, remove filler words and silences, then export an MP4."
  • "Create a new 9:16 project, import the file at ~/Recordings/launch.mov, add bold captions, and preview it."
  • "List all my projects from this week and tell me which one is longest."

OpenClaw routes the request to its agent, which picks the right PandaStudio tools and runs the edit on your machine. Because OpenClaw has memory and runs on a schedule, you can also set up recurring jobs ("every Friday, transcribe my new recordings and draft titles").

Troubleshooting

  • Server won't start — run openclaw mcp doctor pandastudio --probe to see the real error. Most common: PandaStudio's automation server isn't enabled (Step 3), or the token was regenerated.
  • Token env var ignored — OpenClaw blocks some interpreter startup vars for safety, but credential vars like PANDASTUDIO_TOKEN are allowed. Double-check there's no typo in the var name.
  • Changes not taking effect — run openclaw mcp reload after any config edit. It refreshes the active MCP runtimes without bouncing the gateway.